Individual skill
agent-regression-evals
Use before shipping any agent, prompt, model or tool change, or when a pass-rate drop needs a verdict. Runs repeated trials, gates candidate vs baseline with paired statistics in regression_gate.py, checks tool-call trajectories and finds flaky cases.
engineering/agent-regression-evals/skills/agent-regression-evals/SKILL.md
Source commit 9ef0c3c213932e645cc5cbeeb3c35c3a762a2437
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 3, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 29,488
- Repository last updated
- Nov 5, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agentic-ai Repository topic
- anthropic-claude Repository topic
- claude-ai Repository topic
- claude-code Repository topic
- claude-skills Repository topic
- claude-code-skills Repository topic
- ai-coding-agent Repository topic
- claude-code-plugins Repository topic
- developer-tools Repository topic
- openai-codex Repository topic
- data Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 5,413 bytesSKILL.mdcore · 5,413 bytesassets/ci_eval_gate.example.ymlasset · 1,707 bytesassets/eval_case_spec.example.jsonasset · 669 bytesassets/sample_baseline.jsonlasset · 3,774 bytesassets/sample_candidate.jsonlasset · 3,819 bytesreferences/eval_statistics.mddoc · 4,964 bytesreferences/flaky_cases_and_quarantine.mddoc · 4,935 bytesreferences/trajectory_grading.mddoc · 4,249 bytesscripts/flake_detector.pyruns · 10,005 bytesscripts/regression_gate.pyruns · 12,451 bytesscripts/trajectory_checker.pyruns · 10,854 bytes
Read excerpt
# Agent Regression Evals — prove the change did not make it worse
> **Portability:** 3 stdlib scripts, no APIs, no LLM calls. You run the agent; these grade, count and gate.
"Pass rate went from 82% to 79%" is not a finding until you know whether three
points is outside the noise. Agents are non-deterministic, so one trial per
case cannot tell a regression from a coin flip, and a final answer can be right
while the path to it called a tool it never should have.
## Workflow
```bash
# 0 - Run every case k times (k >= 3) on baseline and candidate, from a clean
# environment per trial. Write one JSONL row per trial: